Additional file 1 of Risk factors for adverse outcomes during mechanical ventilation of 1152 COVID-19 patients: a multicenter machine learning study with highly granular data from the Dutch Data Warehouse

Additional file 1: Figure S1. Patient selection. Figure S2. Selection of observations throughout the course of IMV. Figure S3. Nested cross-validation. Figure S4. Importance of the top 10 predictors for the prediction of ventilator free days, as well as the difference for predictors over time. Figure S5. SHAP plot ICU mortality (XGBoost). Figure S6. SHAP plot for ICU free days (XGBoost). Figure S7. SHAP plot for ventilator free days (XGBoost). Figure S8. PDPs. Table S1. Overview of all predictors used in the model with a definition where applicable. Table S2. Overall algorithm performance for... Mehr ...

Verfasser: Lucas M. Fleuren (11033587)
Michele Tonutti (5432471)
Daan P. de Bruin (11033590)
Robbert C. A. Lalisang (11033593)
Tariq A. Dam (11033596)
Diederik Gommers (22889)
Olaf L. Cremer (9984089)
Rob J. Bosman (8847626)
Sebastiaan J. J. Vonk (11033599)
Mattia Fornasa (11033602)
Tomas Machado (11033605)
Nardo J. M. van der Meer (11033608)
Sander Rigter (11033611)
Evert-Jan Wils (8278230)
Tim Frenzel (9586349)
Dave A. Dongelmans (6029318)
Remko de Jong (11033614)
Marco Peters (3768403)
Marlijn J. A. Kamps (11033617)
Dharmanand Ramnarain (11033620)
Ralph Nowitzky (11033623)
Fleur G. C. A. Nooteboom (11033626)
Wouter de Ruijter (293035)
Louise C. Urlings-Strop (11033629)
Ellen G. M. Smit (11033632)
D. Jannet Mehagnoul-Schipper (11033635)
Tom Dormans (10654518)
Cornelis P. C. de Jager (11033638)
Stefaan H. A. Hendriks (11033641)
Evelien Oostdijk (11033644)
Auke C. Reidinga (10654530)
Barbara Festen-Spanjer (11033647)
Gert Brunnekreef (11033650)
Alexander D. Cornet (11033653)
Walter van den Tempel (11033656)
Age D. Boelens (6291731)
Peter Koetsier (11033659)
Judith Lens (11033662)
Sefanja Achterberg (606820)
Harald J. Faber (11033665)
A. Karakus (11033668)
Menno Beukema (11033671)
Robert Entjes (11033674)
Paul de Jong (11033677)
Taco Houwert (11033680)
Hidde Hovenkamp (11033683)
Roberto Noorduijn Londono (11033686)
Davide Quintarelli (11033689)
Martijn G. Scholtemeijer (11033692)
Aletta A. de Beer (11033695)
Giovanni Cinà (11033698)
Martijn Beudel (10654515)
Nicolet F. de Keizer (11033701)
Mark Hoogendoorn (11033704)
Armand R. J. Girbes (8847623)
Willem E. Herter (11033707)
Paul W. G. Elbers (5368067)
Patrick J. Thoral (11033710)
Dokumenttyp: Text
Erscheinungsdatum: 2021
Schlagwörter: Medicine / Biotechnology / Cancer / Biological Sciences not elsewhere classified / Information Systems not elsewhere classified / COVID-19 / Mortality prediction / Risk factors / Machine learning
Sprache: unknown
Permalink: https://search.fid-benelux.de/Record/base-29019057
Datenquelle: BASE; Originalkatalog
Powered By: BASE
Link(s) : https://doi.org/10.6084/m9.figshare.14863519.v1

Additional file 1: Figure S1. Patient selection. Figure S2. Selection of observations throughout the course of IMV. Figure S3. Nested cross-validation. Figure S4. Importance of the top 10 predictors for the prediction of ventilator free days, as well as the difference for predictors over time. Figure S5. SHAP plot ICU mortality (XGBoost). Figure S6. SHAP plot for ICU free days (XGBoost). Figure S7. SHAP plot for ventilator free days (XGBoost). Figure S8. PDPs. Table S1. Overview of all predictors used in the model with a definition where applicable. Table S2. Overall algorithm performance for each of the different outcomes. Table S3. Statistical results for a regression model per outcome. Table S4. Predictor correlations.